{"skill":{"slug":"long-run-harness","displayName":"long-run-harness","summary":"Use when building a Planner→Generator→Evaluator multi-agent harness with the Claude SDK. Triggers: \"build a harness\", \"multi-agent pipeline\", \"agent loop\", \"...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":19,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1777768593480,"updatedAt":1777768906784},"latestVersion":{"version":"1.0.0","createdAt":1777768593480,"changelog":"Initial release of the skill for building multi-agent Claude SDK harnesses.\n\n- Guides users through designing and implementing a Planner→Generator→Evaluator orchestrator using `claude-agent-sdk`.\n- Enforces best practices: config-driven parameters, explicit agent looping, and robust evaluation logic.\n- Provides detailed, phase-based instructions for harness structure, agent implementation, and iteration management.\n- Highlights common mistakes and when to simplify the harness.","license":"MIT-0"},"metadata":null,"owner":{"handle":"is-xins-xiaobai","userId":"s172tp4s5nf8cg185rj65rkxe984bht0","displayName":"小白","image":"https://avatars.githubusercontent.com/u/268746679?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious","suspicious.vt_suspicious"],"summary":"Detected: suspicious.llm_suspicious, suspicious.vt_suspicious","engineVersion":"v2.4.22","updatedAt":1777768906784}}